{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BYP3EDXS64SMWB6ENJ7UJJ2HWR","short_pith_number":"pith:BYP3EDXS","schema_version":"1.0","canonical_sha256":"0e1fb20ef2f724cb07c46a7f44a747b467c87bb76afa580c953c19e8ef98f707","source":{"kind":"arxiv","id":"2605.01482","version":3},"attestation_state":"computed","paper":{"title":"Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Grounding multi-hop fact verification in a structural causal model and optimizing it with group relative policy optimization yields more accurate and less hallucinated reasoning than standard chain-of-thought methods.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Askar Hamdulla, Baohua Zhang, Chunxiao Gao, Guotong Geng, Huaping Zhang, Juan Wang, Qiuchi Li, Quan Zhang, Shuai Lei, Yunbo Cao, Yunhan Bu, Zhunchen Luo","submitted_at":"2026-05-02T15:05:38Z","abstract_excerpt":"Multi-Hop Fact Verification requires complex reasoning across disparate evidence, posing significant challenges for Large Language Models , which may suffer from hallucinations and fractured logical chains. Existing methods, while improving transparency via Chain-of-Thought , often lack explicit modeling of the structural dependencies between evidence and claims. In this work, we introduce an SCM-inspired framework that grounds reasoning in explicit directed dependency graphs, treating verification as a constructive structural reasoning process rather than full causal inference with interventi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.01482","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T15:05:38Z","cross_cats_sorted":[],"title_canon_sha256":"71e14239f79f5c4f86636cb7a3888b965dfeb42fa3ba80670f22295bdb5a1e08","abstract_canon_sha256":"05a6525bd4ceedf8bbd193e91497d6ede74be7fd164567922e83a8be1297b8d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:28.377352Z","signature_b64":"7ZxLggv/TTyIkW6qzmmbQgAYT2vj5bsLTW0CM/BUVGIvoaBCysovJGHWlJGfLLY3ZSZFJGWE3Hvuty3Eyml2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e1fb20ef2f724cb07c46a7f44a747b467c87bb76afa580c953c19e8ef98f707","last_reissued_at":"2026-06-24T01:14:28.376907Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:28.376907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Grounding multi-hop fact verification in a structural causal model and optimizing it with group relative policy optimization yields more accurate and less hallucinated reasoning than standard chain-of-thought methods.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Askar Hamdulla, Baohua Zhang, Chunxiao Gao, Guotong Geng, Huaping Zhang, Juan Wang, Qiuchi Li, Quan Zhang, Shuai Lei, Yunbo Cao, Yunhan Bu, Zhunchen Luo","submitted_at":"2026-05-02T15:05:38Z","abstract_excerpt":"Multi-Hop Fact Verification requires complex reasoning across disparate evidence, posing significant challenges for Large Language Models , which may suffer from hallucinations and fractured logical chains. Existing methods, while improving transparency via Chain-of-Thought , often lack explicit modeling of the structural dependencies between evidence and claims. In this work, we introduce an SCM-inspired framework that grounds reasoning in explicit directed dependency graphs, treating verification as a constructive structural reasoning process rather than full causal inference with interventi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments on HoVer and EX-FEVER demonstrate that our SCM-GRPO framework significantly outperforms state-of-the-art baselines, offering a reliable and interpretable solution for complex fact verification.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That explicitly modeling verification as a constructive causal inference process inside a structural causal model will produce more accurate and less hallucinated reasoning chains than standard chain-of-thought methods without introducing new modeling errors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SCM-GRPO grounds multi-hop fact verification in structural causal models and applies GRPO reinforcement learning to optimize reasoning chain length, outperforming baselines on HoVer and EX-FEVER.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Grounding multi-hop fact verification in a structural causal model and optimizing it with group relative policy optimization yields more accurate and less hallucinated reasoning than standard chain-of-thought methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"636cbfab7982b04d7adc59da33ab930f5dad07a1306fd149fdd29a6729eb74b1"},"source":{"id":"2605.01482","kind":"arxiv","version":3},"verdict":{"id":"28a751db-2df2-43aa-9963-4ae9fb9fa3ef","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T02:12:57.703359Z","strongest_claim":"Extensive experiments on HoVer and EX-FEVER demonstrate that our SCM-GRPO framework significantly outperforms state-of-the-art baselines, offering a reliable and interpretable solution for complex fact verification.","one_line_summary":"SCM-GRPO grounds multi-hop fact verification in structural causal models and applies GRPO reinforcement learning to optimize reasoning chain length, outperforming baselines on HoVer and EX-FEVER.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That explicitly modeling verification as a constructive causal inference process inside a structural causal model will produce more accurate and less hallucinated reasoning chains than standard chain-of-thought methods without introducing new modeling errors.","pith_extraction_headline":"Grounding multi-hop fact verification in a structural causal model and optimizing it with group relative policy optimization yields more accurate and less hallucinated reasoning than standard chain-of-thought methods."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.01482/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T17:41:07.373009Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:14:37.062627Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"24620f8e0b5165dab834ba9b01c0cec52100a6cea05b6ea10314ac478cc9440a"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e7e4508c0f2eaf08a47bda52dfce33fbe70217368bacb5502d074829a5e3046f"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.01482","created_at":"2026-06-24T01:14:28.376967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.01482v3","created_at":"2026-06-24T01:14:28.376967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01482","created_at":"2026-06-24T01:14:28.376967+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYP3EDXS64SM","created_at":"2026-06-24T01:14:28.376967+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYP3EDXS64SMWB6E","created_at":"2026-06-24T01:14:28.376967+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYP3EDXS","created_at":"2026-06-24T01:14:28.376967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR","json":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR.json","graph_json":"https://pith.science/api/pith-number/BYP3EDXS64SMWB6ENJ7UJJ2HWR/graph.json","events_json":"https://pith.science/api/pith-number/BYP3EDXS64SMWB6ENJ7UJJ2HWR/events.json","paper":"https://pith.science/paper/BYP3EDXS"},"agent_actions":{"view_html":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR","download_json":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR.json","view_paper":"https://pith.science/paper/BYP3EDXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.01482&json=true","fetch_graph":"https://pith.science/api/pith-number/BYP3EDXS64SMWB6ENJ7UJJ2HWR/graph.json","fetch_events":"https://pith.science/api/pith-number/BYP3EDXS64SMWB6ENJ7UJJ2HWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR/action/storage_attestation","attest_author":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR/action/author_attestation","sign_citation":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR/action/citation_signature","submit_replication":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR/action/replication_record"}},"created_at":"2026-06-24T01:14:28.376967+00:00","updated_at":"2026-06-24T01:14:28.376967+00:00"}